Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It discloses that it uses the caller's gateway credentials and that 'charges and authorization are determined by the gateway,' which is useful billing context, and the nested body notes price snapshots and 'no purchases/account access.' Since the returned schema already lists fields, the addition of credential/charge behavior is the key value, though read-only status and rate limits are not explicitly restated in the main description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the resource and its returned fields before moving to parameter explanation and the credential note. The field enumeration is dense but appropriate for a defined lookup; sentences are efficient with little waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read tool with no output schema, the description enumerates all returned fields, clarifies both parameters, and notes credential/charge behavior and snapshot pricing. An agent has enough to call it correctly; the only minor gap is absence of explicit read-only/failure behavior in the top-level text.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description explains that `app` accepts either a Steam app id or a store URL and that `country` selects the price region (us, de, …) — genuine meaning that the schema's `app` field leaves blank (its description is empty). This compensates well and adds real value beyond the structured schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource ('One game on Steam') and enumerates exactly what is returned: name, price/discount by region, developers, publishers, release date, genres, tags, Metacritic, review counts/verdict, platforms, short description. An agent can immediately tell this is a single-app Steam detail lookup, distinct from sibling crawl4ai tools (shopify products, remoteok jobs, etc.).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description says it fetches details for 'one game,' which implies a single-item lookup and rules out bulk/list use, but it never gives explicit when-to-use guidance or names an alternative for scenarios like searching or comparing games. Usage is inferable rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.